Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.23318 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915617415626752 |
|---|---|
| author | Cao, Jiajun Zhang, Qizhe Jia, Peidong Zhao, Xuhui Lan, Bo Zhang, Xiaoan Li, Zhuo Wei, Xiaobao Chen, Sixiang Li, Liyun Liu, Xianming Lu, Ming Wang, Yang Zhang, Shanghang |
| author_facet | Cao, Jiajun Zhang, Qizhe Jia, Peidong Zhao, Xuhui Lan, Bo Zhang, Xiaoan Li, Zhuo Wei, Xiaobao Chen, Sixiang Li, Liyun Liu, Xianming Lu, Ming Wang, Yang Zhang, Shanghang |
| contents | Vision-Language-Action (VLA) models have demonstrated significant potential in complex scene understanding and action reasoning, leading to their increasing adoption in end-to-end autonomous driving systems. However, the long visual tokens of VLA models greatly increase computational costs. Current visual token pruning methods in Vision-Language Models (VLM) rely on either visual token similarity or visual-text attention, but both have shown poor performance in autonomous driving scenarios. Given that human drivers concentrate on relevant foreground areas while driving, we assert that retaining visual tokens containing this foreground information is essential for effective decision-making. Inspired by this, we propose FastDriveVLA, a novel reconstruction-based vision token pruning framework designed specifically for autonomous driving. FastDriveVLA includes a plug-and-play visual token pruner called ReconPruner, which prioritizes foreground information through MAE-style pixel reconstruction. A novel adversarial foreground-background reconstruction strategy is designed to train ReconPruner for the visual encoder of VLA models. Once trained, ReconPruner can be seamlessly applied to different VLA models with the same visual encoder without retraining. To train ReconPruner, we also introduce a large-scale dataset called nuScenes-FG, consisting of 241K image-mask pairs with annotated foreground regions. Our approach achieves state-of-the-art results on the nuScenes open-loop planning benchmark across different pruning ratios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_23318 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FastDriveVLA: Efficient End-to-End Driving via Plug-and-Play Reconstruction-based Token Pruning Cao, Jiajun Zhang, Qizhe Jia, Peidong Zhao, Xuhui Lan, Bo Zhang, Xiaoan Li, Zhuo Wei, Xiaobao Chen, Sixiang Li, Liyun Liu, Xianming Lu, Ming Wang, Yang Zhang, Shanghang Computer Vision and Pattern Recognition Artificial Intelligence Vision-Language-Action (VLA) models have demonstrated significant potential in complex scene understanding and action reasoning, leading to their increasing adoption in end-to-end autonomous driving systems. However, the long visual tokens of VLA models greatly increase computational costs. Current visual token pruning methods in Vision-Language Models (VLM) rely on either visual token similarity or visual-text attention, but both have shown poor performance in autonomous driving scenarios. Given that human drivers concentrate on relevant foreground areas while driving, we assert that retaining visual tokens containing this foreground information is essential for effective decision-making. Inspired by this, we propose FastDriveVLA, a novel reconstruction-based vision token pruning framework designed specifically for autonomous driving. FastDriveVLA includes a plug-and-play visual token pruner called ReconPruner, which prioritizes foreground information through MAE-style pixel reconstruction. A novel adversarial foreground-background reconstruction strategy is designed to train ReconPruner for the visual encoder of VLA models. Once trained, ReconPruner can be seamlessly applied to different VLA models with the same visual encoder without retraining. To train ReconPruner, we also introduce a large-scale dataset called nuScenes-FG, consisting of 241K image-mask pairs with annotated foreground regions. Our approach achieves state-of-the-art results on the nuScenes open-loop planning benchmark across different pruning ratios. |
| title | FastDriveVLA: Efficient End-to-End Driving via Plug-and-Play Reconstruction-based Token Pruning |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2507.23318 |